On Evaluation of Document Classification using RVL-CDIP
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:7CWRI3VFrecord.jsonopen to challenge →
read the original abstract
The RVL-CDIP benchmark is widely used for measuring performance on the task of document classification. Despite its widespread use, we reveal several undesirable characteristics of the RVL-CDIP benchmark. These include (1) substantial amounts of label noise, which we estimate to be 8.1% (ranging between 1.6% to 16.9% per document category); (2) presence of many ambiguous or multi-label documents; (3) a large overlap between test and train splits, which can inflate model performance metrics; and (4) presence of sensitive personally-identifiable information like US Social Security numbers (SSNs). We argue that there is a risk in using RVL-CDIP for benchmarking document classifiers, as its limited scope, presence of errors (state-of-the-art models now achieve accuracy error rates that are within our estimated label error rate), and lack of diversity make it less than ideal for benchmarking. We further advocate for the creation of a new document classification benchmark, and provide recommendations for what characteristics such a resource should include.
This paper has not been read by Pith yet.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.